A multi-level classification based ensemble and feature extractor for credit risk assessment
With the growth of people’s demand for loans, banks and other financial institutions put forward higher requirements for customer credit risk level classification, the purpose is to make better loan decisions and loan amount allocation and reduce the pre-loan risk. This article proposes a Multi-Leve...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2024-02-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-1915.pdf |
_version_ | 1797284202344873984 |
---|---|
author | Yuanyuan Wang Zhuang Wu Jing Gao Chenjun Liu Fangfang Guo |
author_facet | Yuanyuan Wang Zhuang Wu Jing Gao Chenjun Liu Fangfang Guo |
author_sort | Yuanyuan Wang |
collection | DOAJ |
description | With the growth of people’s demand for loans, banks and other financial institutions put forward higher requirements for customer credit risk level classification, the purpose is to make better loan decisions and loan amount allocation and reduce the pre-loan risk. This article proposes a Multi-Level Classification based Ensemble and Feature Extractor (MLCEFE) that incorporates the strengths of sampling, feature extraction, and ensemble classification. MLCEFE uses SMOTE + Tomek links to solve the problem of data imbalance and then uses a deep neural network (DNN), auto-encoder (AE), and principal component analysis (PCA) to transform the original variables into higher-level abstract features for feature extraction. Finally, it combined multiple ensemble learners to improve the effect of personal credit risk multi-classification. During performance evaluation, MLCEFE has shown remarkable results in the multi-classification of personal credit risk compared with other classification methods. |
first_indexed | 2024-03-07T17:44:34Z |
format | Article |
id | doaj.art-284dcaac8b6d4796ae31d472382578f7 |
institution | Directory Open Access Journal |
issn | 2376-5992 |
language | English |
last_indexed | 2024-03-07T17:44:34Z |
publishDate | 2024-02-01 |
publisher | PeerJ Inc. |
record_format | Article |
series | PeerJ Computer Science |
spelling | doaj.art-284dcaac8b6d4796ae31d472382578f72024-03-02T15:05:58ZengPeerJ Inc.PeerJ Computer Science2376-59922024-02-0110e191510.7717/peerj-cs.1915A multi-level classification based ensemble and feature extractor for credit risk assessmentYuanyuan WangZhuang WuJing GaoChenjun LiuFangfang GuoWith the growth of people’s demand for loans, banks and other financial institutions put forward higher requirements for customer credit risk level classification, the purpose is to make better loan decisions and loan amount allocation and reduce the pre-loan risk. This article proposes a Multi-Level Classification based Ensemble and Feature Extractor (MLCEFE) that incorporates the strengths of sampling, feature extraction, and ensemble classification. MLCEFE uses SMOTE + Tomek links to solve the problem of data imbalance and then uses a deep neural network (DNN), auto-encoder (AE), and principal component analysis (PCA) to transform the original variables into higher-level abstract features for feature extraction. Finally, it combined multiple ensemble learners to improve the effect of personal credit risk multi-classification. During performance evaluation, MLCEFE has shown remarkable results in the multi-classification of personal credit risk compared with other classification methods.https://peerj.com/articles/cs-1915.pdfPersonal credit riskMulti-level classificationSMOTE + Tomek links samplingEnsemble learning |
spellingShingle | Yuanyuan Wang Zhuang Wu Jing Gao Chenjun Liu Fangfang Guo A multi-level classification based ensemble and feature extractor for credit risk assessment PeerJ Computer Science Personal credit risk Multi-level classification SMOTE + Tomek links sampling Ensemble learning |
title | A multi-level classification based ensemble and feature extractor for credit risk assessment |
title_full | A multi-level classification based ensemble and feature extractor for credit risk assessment |
title_fullStr | A multi-level classification based ensemble and feature extractor for credit risk assessment |
title_full_unstemmed | A multi-level classification based ensemble and feature extractor for credit risk assessment |
title_short | A multi-level classification based ensemble and feature extractor for credit risk assessment |
title_sort | multi level classification based ensemble and feature extractor for credit risk assessment |
topic | Personal credit risk Multi-level classification SMOTE + Tomek links sampling Ensemble learning |
url | https://peerj.com/articles/cs-1915.pdf |
work_keys_str_mv | AT yuanyuanwang amultilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT zhuangwu amultilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT jinggao amultilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT chenjunliu amultilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT fangfangguo amultilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT yuanyuanwang multilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT zhuangwu multilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT jinggao multilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT chenjunliu multilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment AT fangfangguo multilevelclassificationbasedensembleandfeatureextractorforcreditriskassessment |